Beyond Hard Constraints: Budget-Conditioned Reachability For Safe Offline Reinforcement Learning
arXiv:2603.22292v1 Announce Type: new
Abstract: Sequential decision making using Markov Decision Process underpins many realworld applications. Both model-based and model free methods have achieved strong results in these settings. However, real-world tasks must balance reward maximization with saf...
Efficient Embedding-based Synthetic Data Generation for Complex Reasoning Tasks
arXiv:2603.22294v1 Announce Type: new
Abstract: Synthetic Data Generation (SDG), leveraging Large Language Models (LLMs), has recently been recognized and broadly adopted as an effective approach to improve the performance of smaller but more resource and compute efficient LLMs through fine-tuning....
Between the Layers Lies the Truth: Uncertainty Estimation in LLMs Using Intra-Layer Local Information Scores
arXiv:2603.22299v1 Announce Type: new
Abstract: Large language models (LLMs) are often confidently wrong, making reliable uncertainty estimation (UE) essential. Output-based heuristics are cheap but brittle, while probing internal representations is effective yet high-dimensional and hard to transf...
arXiv:2603.22300v1 Announce Type: new
Abstract: Scaling Transformers to ultra-long contexts is bottlenecked by the $O(n^2 d)$ cost of self-attention. Existing methods reduce this cost along the sequence axis through local windows, kernel approximations, or token-level sparsity, but these approaches...
Latent Semantic Manifolds in Large Language Models
arXiv:2603.22301v1 Announce Type: new
Abstract: Large Language Models (LLMs) perform internal computations in continuous vector spaces yet produce discrete tokens -- a fundamental mismatch whose geometric consequences remain poorly understood. We develop a mathematical framework that interprets LLM...
The Efficiency Attenuation Phenomenon: A Computational Challenge to the Language of Thought Hypothesis
arXiv:2603.22312v1 Announce Type: new
Abstract: This paper computationally investigates whether thought requires a language-like format, as posited by the Language of Thought (LoT) hypothesis. We introduce the ``AI Private Language'' thought experiment: if two artificial agents develop an efficient...
Intelligence Inertia: Physical Principles and Applications
arXiv:2603.22347v1 Announce Type: new
Abstract: While Landauer's principle establishes the fundamental thermodynamic floor for information erasure and Fisher Information provides a metric for local curvature in parameter space, these classical frameworks function effectively only as approximations ...
arXiv:2603.22350v1 Announce Type: new
Abstract: Deterministic pre-execution safety gates evaluate whether individual agent actions are compatible with their assigned roles. While effective at per-action authorization, these systems are structurally blind to distributed attacks that decompose harmfu...
Thinking into the Future: Latent Lookahead Training for Transformers
This paper was accepted at the Workshop on Latent & Implicit Thinking – Going Beyond CoT Reasoning 2026 at ICLR.
Autoregressive language models trained with next-token prediction generate text by sampling one discrete token at a time. Although very scalable, this objective forces the model to commit...
We introduce exclusive self attention (XSA), a simple modification of self attention (SA) that improves Transformer’s sequence modeling performance. The key idea is to constrain attention to capture only information orthogonal to the token’s own value vector (thus excluding information of self posit...
What if AI could explain itself? As language models scale in size and complexity, that possibility has drawn growing excitement, and hope. But new research from MIT, Technion, and Northeastern University suggests the reality is much messier, and more concerning...
AgenticGEO: A Self-Evolving Agentic System for Generative Engine Optimization
arXiv:2603.20213v1 Announce Type: new
Abstract: Generative search engines represent a transition from traditional ranking-based retrieval to Large Language Model (LLM)-based synthesis, transforming optimization goals from ranking prominence towards content inclusion. Generative Engine Optimization ...
ProMAS: Proactive Error Forecasting for Multi-Agent Systems Using Markov Transition Dynamics
arXiv:2603.20260v1 Announce Type: new
Abstract: The integration of Large Language Models into Multi-Agent Systems (MAS) has enabled the so-lution of complex, long-horizon tasks through collaborative reasoning. However, this collec-tive intelligence is inherently fragile, as a single logical fallacy...
Domain-Specialized Tree of Thought through Plug-and-Play Predictors
arXiv:2603.20267v1 Announce Type: new
Abstract: While Large Language Models (LLMs) have advanced complex reasoning, prominent methods like the Tree of Thoughts (ToT) framework face a critical trade-off between exploration depth and computational efficiency. Existing ToT implementations often rely o...
FactorSmith: Agentic Simulation Generation via Markov Decision Process Decomposition with Planner-Designer-Critic Refinement
arXiv:2603.20270v1 Announce Type: new
Abstract: Generating executable simulations from natural language specifications remains a challenging problem due to the limited reasoning capacity of large language models (LLMs) when confronted with large, interconnected codebases. This paper presents Factor...
Me, Myself, and $\pi$ : Evaluating and Explaining LLM Introspection
arXiv:2603.20276v1 Announce Type: new
Abstract: A hallmark of human intelligence is Introspection-the ability to assess and reason about one's own cognitive processes. Introspection has emerged as a promising but contested capability in large language models (LLMs). However, current evaluations oft...
JointFM-0.1: A Foundation Model for Multi-Target Joint Distributional Prediction
arXiv:2603.20266v1 Announce Type: new
Abstract: Despite the rapid advancements in Artificial Intelligence (AI), Stochastic Differential Equations (SDEs) remain the gold-standard formalism for modeling systems under uncertainty. However, applying SDEs in practice is fraught with challenges: modeling...
MARLIN: Multi-Agent Reinforcement Learning for Incremental DAG Discovery
arXiv:2603.20295v1 Announce Type: new
Abstract: Uncovering causal structures from observational data is crucial for understanding complex systems and making informed decisions. While reinforcement learning (RL) has shown promise in identifying these structures in the form of a directed acyclic grap...
Collaborative Adaptive Curriculum for Progressive Knowledge Distillation
arXiv:2603.20296v1 Announce Type: new
Abstract: Recent advances in collaborative knowledge distillation have demonstrated cutting-edge performance for resource-constrained distributed multimedia learning scenarios. However, achieving such competitiveness requires addressing a fundamental mismatch: ...
Rolling-Origin Validation Reverses Model Rankings in Multi-Step PM10 Forecasting: XGBoost, SARIMA, and Persistence
arXiv:2603.20315v1 Announce Type: new
Abstract: (a) Many air quality forecasting studies report gains from machine learning, but evaluations often use static chronological splits and omit persistence baselines, so the operational added value under routine updating is unclear.
(b) Using 2,350 dail...
Trained on Tokens, Calibrated on Concepts: The Emergence of Semantic Calibration in LLMs
Large Language Models (LLMs) often lack meaningful confidence estimates for their outputs. While base LLMs are known to exhibit next-token calibration, it remains unclear whether they can assess confidence in the actual meaning of their responses beyond the token level. We find that, when using a ce...
Scaling Synthetic Task Generation for Agents via Exploration
Post-Training Multimodal Large Language Models (MLLMs) to build interactive agents holds promise across domains such as computer-use, web navigation, and robotics. A key challenge in scaling such post-training is lack of high-quality downstream agentic task datasets with tasks that are diverse, feas...
Are machines truly intelligent? AI researchers Subutai Ahmad and Nicolò Fusi join Doug Burger to compare transformer-based AI with the human brain, exploring continual learning, efficiency, and whether today’s models are on a path toward human intelligence.
The post Will machines ever be intelligent...
Speculating Experts Accelerates Inference for Mixture-of-Experts
arXiv:2603.19289v1 Announce Type: new
Abstract: Mixture-of-Experts (MoE) models have gained popularity as a means of scaling the capacity of large language models (LLMs) while maintaining sparse activations and reduced per-token compute. However, in memory-constrained inference settings, expert wei...